{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CDFNKY3NJSZT6CRDHCYDIM2XL5","short_pith_number":"pith:CDFNKY3N","schema_version":"1.0","canonical_sha256":"10cad5636d4cb33f0a2338b03433575f7eaac4951977a6c8134a38ca9407b308","source":{"kind":"arxiv","id":"2407.05138","version":2},"attestation_state":"computed","paper":{"title":"Are LLMs Correctly Integrated into Software Systems?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chengcheng Wan, Jiawei Shen, Lei Ma, Ting Su, Yuchen Shao, Yuheng Huang","submitted_at":"2024-07-06T17:25:11Z","abstract_excerpt":"Large language models (LLMs) provide effective solutions in various application scenarios, with the support of retrieval-augmented generation (RAG). However, developers face challenges in integrating LLM and RAG into software systems, due to lacking interface specifications, various requirements from software context, and complicated system management. In this paper, we have conducted a comprehensive study of 100 open-source applications that incorporate LLMs with RAG support, and identified 18 defect patterns. Our study reveals that 77% of these applications contain more than three types of i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.05138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-07-06T17:25:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a43fe1b3d2014e2fe126ce15c24acaf6a75db1aa779e3b1f970e67330edb75c7","abstract_canon_sha256":"d5848a37755169f95e11fdfad22457daa0bdef52ad6a01d347b38d7e7398d137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:21.835278Z","signature_b64":"FgoVeu12tc/j0rlxuV3Ibg4I7wDbGqiaLj2jIvXoo6LAX6IFTt2mS2VzO+LcdVObJjRAq8r/2bMimTgiI3gYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10cad5636d4cb33f0a2338b03433575f7eaac4951977a6c8134a38ca9407b308","last_reissued_at":"2026-07-05T10:11:21.834733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:21.834733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are LLMs Correctly Integrated into Software Systems?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chengcheng Wan, Jiawei Shen, Lei Ma, Ting Su, Yuchen Shao, Yuheng Huang","submitted_at":"2024-07-06T17:25:11Z","abstract_excerpt":"Large language models (LLMs) provide effective solutions in various application scenarios, with the support of retrieval-augmented generation (RAG). However, developers face challenges in integrating LLM and RAG into software systems, due to lacking interface specifications, various requirements from software context, and complicated system management. In this paper, we have conducted a comprehensive study of 100 open-source applications that incorporate LLMs with RAG support, and identified 18 defect patterns. Our study reveals that 77% of these applications contain more than three types of i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05138","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.05138/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.05138","created_at":"2026-07-05T10:11:21.834794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05138v2","created_at":"2026-07-05T10:11:21.834794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05138","created_at":"2026-07-05T10:11:21.834794+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDFNKY3NJSZT","created_at":"2026-07-05T10:11:21.834794+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDFNKY3NJSZT6CRD","created_at":"2026-07-05T10:11:21.834794+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDFNKY3N","created_at":"2026-07-05T10:11:21.834794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28893","citing_title":"Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22976","citing_title":"LLM Code Smells: A Taxonomy and Detection Approach","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17444","citing_title":"MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5","json":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5.json","graph_json":"https://pith.science/api/pith-number/CDFNKY3NJSZT6CRDHCYDIM2XL5/graph.json","events_json":"https://pith.science/api/pith-number/CDFNKY3NJSZT6CRDHCYDIM2XL5/events.json","paper":"https://pith.science/paper/CDFNKY3N"},"agent_actions":{"view_html":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5","download_json":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5.json","view_paper":"https://pith.science/paper/CDFNKY3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05138&json=true","fetch_graph":"https://pith.science/api/pith-number/CDFNKY3NJSZT6CRDHCYDIM2XL5/graph.json","fetch_events":"https://pith.science/api/pith-number/CDFNKY3NJSZT6CRDHCYDIM2XL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5/action/storage_attestation","attest_author":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5/action/author_attestation","sign_citation":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5/action/citation_signature","submit_replication":"https://pith.science/pith/CDFNKY3NJSZT6CRDHCYDIM2XL5/action/replication_record"}},"created_at":"2026-07-05T10:11:21.834794+00:00","updated_at":"2026-07-05T10:11:21.834794+00:00"}